Papers › Transformer-based Dual Relation Graph for Multi-label Image Recognition

Transformer-based Dual Relation Graph for Multi-label Image Recognition

10 Oct 2021ICCV 2021 10arXiv:2110.04722archive 2025-07-28

Jiawei Zhao, Ke Yan, Yifan Zhao, Xiaowei Guo, Feiyue Huang, Jia Li

The simultaneous recognition of multiple objects in one image remains a challenging task, spanning multiple events in the recognition field such as various object scales, inconsistent appearances, and confused inter-class relationships. Recent research efforts mainly resort to the statistic label co-occurrences and linguistic word embedding to enhance the unclear semantics. Different from these researches, in this paper, we propose a novel Transformer-based Dual Relation learning framework, constructing complementary relationships by exploring two aspects of correlation, i.e., structural relation graph and semantic relation graph. The structural relation graph aims to capture long-range correlations from object context, by developing a cross-scale transformer-based architecture. The semantic graph dynamically models the semantic meanings of image objects with explicit semantic-aware constraints. In addition, we also incorporate the learnt structural relationship into the semantic graph, constructing a joint relation graph for robust representations. With the collaborative learning of these two effective relation graphs, our approach achieves new state-of-the-art on two popular multi-label recognition benchmarks, i.e., MS-COCO and VOC 2007 dataset.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2110.04722")

Code

Syntology Ran 9 of 12 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 8 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 9 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

iCVTEAM/TDRG officialpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested; 9 ran; 0 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
8ran
3unverified

Licence: 0 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from iCVTEAM/TDRG. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

GraphConvolution iCVTEAM/TDRG/models/TDRG.py official repository ran Apache-2.0 (permissive) · 4af7cba6f2b6a00b · report
PositionEmbeddingLearned iCVTEAM/TDRG/models/TDRG.py official repository ran fingerprinted Apache-2.0 (permissive) · 0fdd4b27f23fb10e · report
PositionEmbeddingSine iCVTEAM/TDRG/models/TDRG.py official repository ran Apache-2.0 (permissive) · 19ad134c39cefe3a · report
TopKMaxPooling iCVTEAM/TDRG/models/TDRG.py official repository ran fingerprinted Apache-2.0 (permissive) · b98e254770325b03 · report
TransformerDecoder iCVTEAM/TDRG/models/TDRG.py official repository ran fingerprinted Apache-2.0 (permissive) · e3629529c763edf7 · report
TransformerDecoderLayer iCVTEAM/TDRG/models/TDRG.py official repository ran Apache-2.0 (permissive) · a1044a3d81853ba9 · report
TransformerEncoder iCVTEAM/TDRG/models/TDRG.py official repository ran fingerprinted Apache-2.0 (permissive) · 8ee0966a4a5305fa · report
TransformerEncoderLayer iCVTEAM/TDRG/models/TDRG.py official repository ran Apache-2.0 (permissive) · 4a32b2ac8f43376e · report
build_position_encoding iCVTEAM/TDRG/models/TDRG.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 626421743e751cfd · report
TDRG iCVTEAM/TDRG/models/TDRG.py official repository unverified Apache-2.0 (permissive) · e32b7a1a6935ef81 · report
Transformer iCVTEAM/TDRG/models/TDRG.py official repository unverified Apache-2.0 (permissive) · a6af96a295df827c · report
build_transformer iCVTEAM/TDRG/models/TDRG.py official repository unverified Apache-2.0 (permissive) · 2a6ad2bf42c596fb · report

Tasks

Multi-Label ClassificationMulti-Label Image Recognition

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-Label Classification MS-COCO TDRG-R101(576×576) mAP 86.0 #22 of 34 Archive leaderboard report
Multi-Label Classification MS-COCO TDRG-R101(448×448) mAP 84.6 #26 of 34 Archive leaderboard report
Multi-Label Classification PASCAL VOC 2007 TDRG-R101(448×448) mAP 95.0 #10 of 17 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections